© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 20733
    Prev
    Next
    INDEX
    Explanations

    generated content or files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    old
    -0.10
    æĿ¥èĩª
    -0.10
    _seen
    -0.09
     originals
    -0.09
    (old
    -0.08
    æŧ
    -0.08
    -used
    -0.08
    Seen
    -0.08
    Measured
    -0.08
    -original
    -0.08
    POSITIVE LOGITS
     newly
    0.48
     created
    0.41
     generated
    0.33
    created
    0.32
    Created
    0.32
     Created
    0.30
     Newly
    0.29
    _created
    0.27
    .created
    0.27
     produced
    0.26
    Activations Density 0.175%

    No Known Activations